Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 2276
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bun
    -0.07
    %.↵↵
    -0.07
    edith
    -0.07
    🌫
    -0.07
    kür
    -0.07
    续航
    -0.07
     reducer
    -0.06
    垃圾桶
    -0.06
    architecture
    -0.06
    avers
    -0.06
    POSITIVE LOGITS
     Conte
    0.07
    รายงาน
    0.07
    (infile
    0.07
    'A
    0.07
    也为
    0.07
    :start
    0.07
    ᅣ
    0.07
    .Root
    0.07
    ierre
    0.06
     Risk
    0.06
    Activations Density 0.013%

    No Known Activations